# Generated by `jof250 profiles build` — do not edit by hand (see docs/DATA_DICTIONARY.md)
profile: corpus_all
ontology_version: '1.0'
built:
  timestamp: '2026-11-03T23:29:46+00:00'
  code_version: f8b9e5a-dirty
  host:
    platform: macOS-27.0-arm64-arm-64bit
    python: 3.12.13
    machine: arm64
    node: MacBookPro-de-simon-pierre-2.local
selection_rule: all included train documents
n_documents: 221
split: train (heldout_v1 excluded)
caveat: Observed frequencies describe what published JoF articles did in 2017–2020; they are not evidence that these choices
  are editorially superior or required.
structure:
  pages:
    n: 221
    median: 43.0
    q25: 38.0
    q75: 47.0
    mean: 42.679
    min: 1.0
    max: 67.0
    median_ci95_bootstrap:
    - 42.0
    - 44.0
  n_words_body:
    n: 221
    median: 11009.0
    q25: 10035.0
    q75: 12407.0
    mean: 11137.873
    min: 25.0
    max: 17348.0
    median_ci95_bootstrap:
    - 10813.0
    - 11256.0
  n_words_appendix:
    n: 221
    median: 0.0
    q25: 0.0
    q75: 1599.0
    mean: 934.443
    min: 0.0
    max: 9912.0
    median_ci95_bootstrap:
    - 0.0
    - 23.0
  abstract_words:
    n: 221
    median: 101.0
    q25: 96.0
    q75: 104.0
    mean: 105.385
    min: 0.0
    max: 535.0
    median_ci95_bootstrap:
    - 100.0
    - 102.0
  n_sections:
    n: 221
    median: 5.0
    q25: 5.0
    q75: 6.0
    mean: 5.475
    min: 0.0
    max: 10.0
    median_ci95_bootstrap:
    - 5.0
    - 6.0
  n_subsections:
    n: 221
    median: 14.0
    q25: 10.0
    q75: 19.0
    mean: 14.81
    min: 0.0
    max: 46.0
    median_ci95_bootstrap:
    - 13.0
    - 14.0
  n_paragraphs:
    n: 221
    median: 132.0
    q25: 89.0
    q75: 218.0
    mean: 185.118
    min: 2.0
    max: 920.0
    median_ci95_bootstrap:
    - 118.0
    - 150.525
  n_equations:
    n: 221
    median: 10.0
    q25: 4.0
    q75: 23.0
    mean: 17.62
    min: 0.0
    max: 159.0
    median_ci95_bootstrap:
    - 8.0
    - 12.0
  n_tables:
    n: 221
    median: 8.0
    q25: 6.0
    q75: 11.0
    mean: 7.76
    min: 0.0
    max: 24.0
    median_ci95_bootstrap:
    - 7.0
    - 9.0
  n_figures:
    n: 221
    median: 4.0
    q25: 2.0
    q75: 7.0
    mean: 4.362
    min: 0.0
    max: 14.0
    median_ci95_bootstrap:
    - 3.0
    - 4.0
  n_footnotes:
    n: 221
    median: 37.0
    q25: 29.0
    q75: 48.0
    mean: 40.136
    min: 1.0
    max: 148.0
    median_ci95_bootstrap:
    - 35.0
    - 39.0
  n_references:
    n: 221
    median: 52.0
    q25: 41.0
    q75: 64.0
    mean: 54.158
    min: 0.0
    max: 198.0
    median_ci95_bootstrap:
    - 49.0
    - 56.0
  n_citations_in_text:
    n: 221
    median: 55.0
    q25: 38.0
    q75: 72.0
    mean: 59.995
    min: 0.0
    max: 205.0
    median_ci95_bootstrap:
    - 50.475
    - 61.0
  intro_words:
    n: 221
    median: 1804.0
    q25: 1568.0
    q75: 2132.0
    mean: 1831.249
    min: 25.0
    max: 3245.0
    median_ci95_bootstrap:
    - 1754.0
    - 1861.3
  intro_paragraphs:
    n: 221
    median: 7.0
    q25: 6.0
    q75: 9.0
    mean: 8.344
    min: 1.0
    max: 64.0
    median_ci95_bootstrap:
    - 7.0
    - 8.0
  intro_share:
    n: 221
    median: 0.164
    q25: 0.14
    q75: 0.192
    mean: 0.174
    min: 0.071
    max: 1.0
    median_ci95_bootstrap:
    - 0.16
    - 0.172
  conclusion_words:
    n: 221
    median: 358.0
    q25: 254.0
    q75: 511.0
    mean: 454.783
    min: 0.0
    max: 3986.0
    median_ci95_bootstrap:
    - 326.0
    - 393.525
  conclusion_share:
    n: 221
    median: 0.032
    q25: 0.023
    q75: 0.046
    mean: 0.042
    min: 0.0
    max: 0.427
    median_ci95_bootstrap:
    - 0.031
    - 0.035
  theory_share:
    n: 221
    median: 0.086
    q25: 0.0
    q75: 0.251
    mean: 0.148
    min: 0.0
    max: 0.817
    median_ci95_bootstrap:
    - 0.027
    - 0.137
  data_share:
    n: 221
    median: 0.0
    q25: 0.0
    q75: 0.116
    mean: 0.071
    min: 0.0
    max: 0.57
    median_ci95_bootstrap:
    - 0.0
    - 0.056
  results_share:
    n: 221
    median: 0.0
    q25: 0.0
    q75: 0.151
    mean: 0.099
    min: 0.0
    max: 0.627
    median_ci95_bootstrap:
    - 0.0
    - 0.0
  robustness_share:
    n: 221
    median: 0.0
    q25: 0.0
    q75: 0.053
    mean: 0.04
    min: 0.0
    max: 0.344
    median_ci95_bootstrap:
    - 0.0
    - 0.0
  words_per_table:
    n: 221
    median: 1354.5
    q25: 1006.375
    q75: 2017.571
    mean: 2712.665
    min: 25.0
    max: 17169.0
    median_ci95_bootstrap:
    - 1217.333
    - 1448.333
  refs_per_1000_words:
    n: 221
    median: 4.748
    q25: 3.675
    q75: 5.905
    mean: 4.882
    min: 0.0
    max: 13.377
    median_ci95_bootstrap:
    - 4.52
    - 5.017
  equations_per_1000_words:
    n: 221
    median: 0.886
    q25: 0.338
    q75: 2.248
    mean: 1.732
    min: 0.0
    max: 23.044
    median_ci95_bootstrap:
    - 0.688
    - 1.16
presence:
  has_robustness_section:
    n: 221
    share: 0.262
  has_literature_section:
    n: 221
    share: 0.172
  has_appendix:
    n: 221
    share: 0.498
  has_internet_appendix:
    n: 221
    share: 0.887
by_year:
  2017:
    n: 51
    n_words_body_median: 10858.0
    n_tables_median: 9.0
  2018:
    n: 52
    n_words_body_median: 11474.5
    n_tables_median: 7.0
  2019:
    n: 59
    n_words_body_median: 10823.0
    n_tables_median: 8.0
  2020:
    n: 59
    n_words_body_median: 11115.0
    n_tables_median: 9.0
rhetoric:
  n_annotated: 221
  genre:
    n: 221
    empirical: 0.529
    mixed_theory_empirical: 0.253
    theoretical: 0.145
    replication_or_correction: 0.032
    methodological_econometric: 0.027
    survey_or_address: 0.014
  subfield:
    n: 221
    asset_pricing: 0.312
    corporate_finance: 0.176
    financial_intermediation_banking: 0.127
    household_finance: 0.1
    market_microstructure: 0.1
    behavioral_finance: 0.054
    macro_finance: 0.045
    entrepreneurial_finance_private_equity: 0.041
  primary_method:
    n: 221
    reduced_form_regression: 0.367
    theoretical_model_analytical: 0.195
    difference_in_differences: 0.1
    structural_estimation: 0.068
    calibration_simulation: 0.063
    instrumental_variables: 0.059
    other: 0.05
    survey_or_experiment: 0.036
  abstract_moves_present:
    question:
      n: 221
      share: 0.701
    gap:
      n: 221
      share: 0.14
    method:
      n: 221
      share: 0.828
    results:
      n: 221
      share: 0.991
    magnitude:
      n: 221
      share: 0.235
    contribution:
      n: 221
      share: 0.692
  abstract_move_order_median_sentence:
    question:
      n: 155
      median: 0.0
      q25: 0.0
      q75: 0.0
      mean: 0.174
      min: 0.0
      max: 4.0
      median_ci95_bootstrap:
      - 0.0
      - 0.0
    gap:
      n: 31
      median: 1.0
      q25: 0.0
      q75: 1.0
      mean: 0.871
      min: 0.0
      max: 4.0
      median_ci95_bootstrap:
      - 0.0
      - 1.0
    method:
      n: 183
      median: 1.0
      q25: 0.0
      q75: 2.0
      mean: 1.055
      min: 0.0
      max: 5.0
      median_ci95_bootstrap:
      - 1.0
      - 1.0
    results:
      n: 219
      median: 1.0
      q25: 1.0
      q75: 2.0
      mean: 1.626
      min: 0.0
      max: 5.0
      median_ci95_bootstrap:
      - 1.0
      - 2.0
    magnitude:
      n: 52
      median: 2.0
      q25: 1.0
      q75: 3.0
      mean: 2.115
      min: 0.0
      max: 5.0
      median_ci95_bootstrap:
      - 2.0
      - 2.0
    contribution:
      n: 153
      median: 3.0
      q25: 1.0
      q75: 4.0
      mean: 2.497
      min: 0.0
      max: 7.0
      median_ci95_bootstrap:
      - 2.0
      - 3.0
  abstract_sentences:
    n: 221
    median: 5.0
    q25: 4.0
    q75: 6.0
    mean: 5.29
    min: 0.0
    max: 16.0
    median_ci95_bootstrap:
    - 5.0
    - 5.0
  magnitude_in_abstract_regex:
    n: 221
    share: 0.176
  introduction:
    paragraphs:
      n: 221
      median: 7.0
      q25: 6.0
      q75: 9.0
      mean: 8.344
      min: 1.0
      max: 64.0
      median_ci95_bootstrap:
      - 7.0
      - 8.0
    words:
      n: 221
      median: 1087.0
      q25: 870.0
      q75: 1320.0
      mean: 1101.919
      min: 25.0
      max: 2771.0
      median_ci95_bootstrap:
      - 1015.0
      - 1140.0
    contribution_paragraph_index:
      n: 210
      median: 4.0
      q25: 1.0
      q75: 6.0
      mean: 4.314
      min: 0.0
      max: 56.0
      median_ci95_bootstrap:
      - 3.0
      - 5.0
    contribution_relative_position:
      n: 210
      median: 0.577
      q25: 0.129
      q75: 0.778
      mean: 0.474
      min: 0.0
      max: 0.941
      median_ci95_bootstrap:
      - 0.5
      - 0.625
    first_move:
      n: 221
      motivation: 0.887
      tension_or_puzzle: 0.027
      preview_of_approach: 0.027
      other: 0.023
      contribution_statement: 0.014
      literature_gap: 0.009
      related_literature_positioning: 0.009
      mechanism_or_theory_sketch: 0.005
    move_prevalence:
      n: 221
      preview_of_results:
        share: 0.95
        median_relative_position: 0.37
      motivation:
        share: 0.932
        median_relative_position: 0.0
      preview_of_approach:
        share: 0.873
        median_relative_position: 0.23
      related_literature_positioning:
        share: 0.864
        median_relative_position: 0.73
      mechanism_or_theory_sketch:
        share: 0.819
        median_relative_position: 0.33
      contribution_statement:
        share: 0.774
        median_relative_position: 0.73
      roadmap:
        share: 0.624
        median_relative_position: 1.0
      literature_gap:
        share: 0.511
        median_relative_position: 0.12
      tension_or_puzzle:
        share: 0.498
        median_relative_position: 0.11
      identification_defense:
        share: 0.425
        median_relative_position: 0.5
      policy_or_broader_implication:
        share: 0.367
        median_relative_position: 0.79
      robustness_mention:
        share: 0.285
        median_relative_position: 0.62
      other:
        share: 0.158
        median_relative_position: 0.69
    moves_per_intro:
      n: 221
      median: 12.0
      q25: 10.0
      q75: 13.0
      mean: 11.679
      min: 1.0
      max: 23.0
      median_ci95_bootstrap:
      - 11.0
      - 12.0
    common_move_sequences:
      n: 221
      ? motivation > preview_of_approach > identification_defense > mechanism_or_theory_sketch > preview_of_approach > preview_of_results
        > robustness_mention > identification_defense > contribution_statement > related_literature_positioning > other >
        policy_or_broader_implication
      : 0.005
      ? motivation > tension_or_puzzle > mechanism_or_theory_sketch > preview_of_results > related_literature_positioning
        > literature_gap > contribution_statement > policy_or_broader_implication > roadmap
      : 0.005
      ? motivation > mechanism_or_theory_sketch > preview_of_results > preview_of_approach > preview_of_results > identification_defense
        > preview_of_results > robustness_mention > related_literature_positioning > contribution_statement
      : 0.005
      ? motivation > policy_or_broader_implication > mechanism_or_theory_sketch > tension_or_puzzle > preview_of_approach
        > preview_of_results > identification_defense > related_literature_positioning > contribution_statement > related_literature_positioning
      : 0.005
      ? motivation > literature_gap > policy_or_broader_implication > preview_of_approach > preview_of_results > robustness_mention
        > preview_of_results > contribution_statement > related_literature_positioning
      : 0.005
      ? tension_or_puzzle > literature_gap > contribution_statement > preview_of_approach > mechanism_or_theory_sketch > identification_defense
        > preview_of_approach > identification_defense > preview_of_results > preview_of_approach > preview_of_results > policy_or_broader_implication
        > related_literature_positioning > roadmap
      : 0.005
    roadmap_present_llm:
      n: 221
      share: 0.629
    roadmap_present_regex:
      n: 221
      share: 0.597
    literature_positioning_location:
      n: 221
      inside_introduction: 0.869
      both: 0.09
      separate_section: 0.027
      none: 0.014
    contribution_types:
      n: 438
      new_evidence: 0.411
      new_theory_or_model: 0.196
      new_data_or_measure: 0.162
      new_identification: 0.084
      resolution_of_puzzle: 0.071
      new_method: 0.05
      replication_or_correction: 0.018
      synthesis: 0.007
  identification:
    causal_language_strength:
      n: 221
      median: 3.0
      q25: 2.0
      q75: 3.0
      mean: 2.575
      min: 1.0
      max: 5.0
      median_ci95_bootstrap:
      - 2.0
      - 3.0
    uses_causal_claim:
      n: 221
      share: 0.498
  results:
    economic_significance_discussed:
      n: 221
      share: 0.787
    statistical_language:
      n: 221
      unclear: 0.787
      stars_and_tstats: 0.109
      mixed: 0.077
      confidence_intervals: 0.014
      p_values: 0.014
    magnitude_statements_in_intro:
      n: 221
      share: 0.57
  robustness:
    location:
      n: 221
      mixed: 0.367
      within_results: 0.235
      none_seen: 0.176
      main_text_section: 0.154
      appendix: 0.05
      internet_appendix: 0.018
    types:
      n: 607
      alternative_specification: 0.229
      other: 0.171
      subsample: 0.17
      alternative_measure: 0.16
      ? ''
      : 0.064
      alternative_sample_period: 0.058
      sensitivity_to_parameters: 0.056
      placebo: 0.048
  tables:
    standard_errors:
      n: 221
      unclear: 0.62
      none: 0.217
      clustered: 0.059
      mixed: 0.041
      newey_west: 0.032
      robust: 0.027
      bootstrap: 0.005
    units_in_notes:
      n: 221
      share: 0.679
    clustered_regex:
      n: 221
      share: 0.054
  figures:
    uncertainty_shown:
      n: 221
      unclear: 0.475
      'no': 0.317
      mixed: 0.095
      no_figures: 0.095
      'yes': 0.018
  conclusion:
    bounded_claims:
      n: 221
      share: 0.819
    policy_implications:
      n: 221
      share: 0.367
    open_questions:
      n: 221
      share: 0.371
  hedging:
    n: 221
    moderate: 0.873
    low: 0.127
  claims_with_stated_evidence_share:
    n: 221
    median: 1.0
    q25: 1.0
    q75: 1.0
    mean: 0.981
    min: 0.0
    max: 1.0
    median_ci95_bootstrap:
    - 1.0
    - 1.0
  llm_vs_rule_section_role_agreement:
    n: 221
    median: 1.0
    q25: 0.8
    q75: 1.0
    mean: 0.896
    min: 0.0
    max: 1.0
    median_ci95_bootstrap:
    - 0.91
    - 1.0
  llm_confidence:
    n: 221
    median: 0.8
    q25: 0.8
    q75: 0.85
    mean: 0.815
    min: 0.75
    max: 0.95
    median_ci95_bootstrap:
    - 0.8
    - 0.8